ai-safety-foundation / sparse_autoencoderLinks
Sparse Autoencoder for Mechanistic Interpretability
☆250Updated 11 months ago
Alternatives and similar repositories for sparse_autoencoder
Users that are interested in sparse_autoencoder are comparing it to the libraries listed below
Sorting:
- Using sparse coding to find distributed representations used by neural networks.☆255Updated last year
- ☆308Updated last month
- ☆227Updated 8 months ago
- Sparsify transformers with SAEs and transcoders☆568Updated last week
- Mechanistic Interpretability Visualizations using React☆257Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆202Updated 6 months ago
- ☆121Updated last year
- ☆101Updated 3 weeks ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆185Updated last week
- ☆173Updated 2 months ago
- ☆131Updated 7 months ago
- Training Sparse Autoencoders on Language Models☆837Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆593Updated this week
- ☆44Updated 7 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- ☆493Updated 11 months ago
- Steering Llama 2 with Contrastive Activation Addition☆158Updated last year
- ☆120Updated 10 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆124Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆57Updated 2 weeks ago
- ☆95Updated 4 months ago
- This repository collects all relevant resources about interpretability in LLMs☆358Updated 7 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- ☆163Updated 7 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆275Updated 2 weeks ago
- Sparse Autoencoder Training Library☆52Updated last month
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆97Updated 4 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆500Updated last year